Multimodal · Benchmark profile

AI2D test split

A diagram understanding benchmark focused on scientific and educational visual question answering.

Reference2026Active2 models

Data verified 1 Aug 2026 · Methodology 2.3.0

Benchmark score on AI2D test split

Leaderboard · 2 models

Qwen3.6-35B-A3B leads at 92.7%, followed by Nemotron 3 Nano Omni 30B A3B (88.5%).

Display onlyMultimodal2026

#1Open

Qwen3.6-35B-A3B

Alibaba Cloud

Qwen/Qwen3.6-35B-A3B

92.7%

Overall #69 · Context 262K tokens

#2Open

Nemotron 3 Nano Omni 30B A3B

NVIDIA

nemotron-3-nano-omni-30b-a3b

88.5%

Overall — · Context 256K tokens

ViewModelsColours

Alibaba CloudNVIDIA

Lumina

AI2D test split leaderboard

Accessible data for AI2D test split leaderboard
Model	Rank	Model ID	Provider	Score	Unit
Qwen3.6-35B-A3B	#1	qwen3-6-35b-a3b	Alibaba Cloud	92.7	percent
Nemotron 3 Nano Omni 30B A3B	#2	nemotron-3-nano-omni-30b-a3b	NVIDIA	88.5	percent

Benchmark score table (2 models)

One best compatible score per canonical product · higher is better

AI2D test split leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B	Alibaba Cloud	open	Source carrier	92.7%
#2	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Source carrier	88.5%

Configuration-preserving evidencePublished source rows (6)Exact source labels, configurations, versions and dated observations. Same-snapshot canonical/configuration projections are shown once.

Every distinct dated source-published row for AI2D test split, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Compare top models

Qwen3.6-35B-A3B vs Nemotron 3 Nano Omni 30B A3B

About AI2D test split

Definition and scoring

Organisation: Qwen
Category: Multimodal
Version: 2026
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

A diagram understanding benchmark focused on scientific and educational visual question answering. Every genuine source row stays tied to its exact model label, configuration, benchmark version and evaluation system. The summary chart shows one best compatible score per canonical product; Score 2.0 admits only explicitly mapped, frozen protocols and keeps incompatible configurations separate.

Open benchmark source ↗

FAQ

Quick answers

What does AI2D test split measure?

A diagram understanding benchmark focused on scientific and educational visual question answering.

Which model scores highest on AI2D test split?

Qwen3.6-35B-A3B by Alibaba Cloud currently leads with 92.7%.

How many models are evaluated on AI2D test split?

2 canonical model products have a qualifying score, backed by 6 distinct dated source rows.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Multimodal · Benchmark profile

AI2D test split

A diagram understanding benchmark focused on scientific and educational visual question answering.

Reference2026Active2 models

Data verified 1 Aug 2026 · Methodology 2.3.0

Benchmark score on AI2D test split

Leaderboard · 2 models

Qwen3.6-35B-A3B leads at 92.7%, followed by Nemotron 3 Nano Omni 30B A3B (88.5%).

Display onlyMultimodal2026

#1Open

Qwen3.6-35B-A3B

Alibaba Cloud

Qwen/Qwen3.6-35B-A3B

92.7%

Overall #69 · Context 262K tokens

#2Open

Nemotron 3 Nano Omni 30B A3B

NVIDIA

nemotron-3-nano-omni-30b-a3b

88.5%

Overall — · Context 256K tokens

ViewModelsColours

Alibaba CloudNVIDIA

Lumina

AI2D test split leaderboard

Accessible data for AI2D test split leaderboard
Model	Rank	Model ID	Provider	Score	Unit
Qwen3.6-35B-A3B	#1	qwen3-6-35b-a3b	Alibaba Cloud	92.7	percent
Nemotron 3 Nano Omni 30B A3B	#2	nemotron-3-nano-omni-30b-a3b	NVIDIA	88.5	percent

Benchmark score table (2 models)

One best compatible score per canonical product · higher is better

AI2D test split leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B	Alibaba Cloud	open	Source carrier	92.7%
#2	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Source carrier	88.5%

Configuration-preserving evidencePublished source rows (6)Exact source labels, configurations, versions and dated observations. Same-snapshot canonical/configuration projections are shown once.

Every distinct dated source-published row for AI2D test split, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	92.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	88.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Compare top models

Qwen3.6-35B-A3B vs Nemotron 3 Nano Omni 30B A3B

About AI2D test split

Definition and scoring

Organisation: Qwen
Category: Multimodal
Version: 2026
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

Open benchmark source ↗

FAQ

Quick answers

What does AI2D test split measure?

A diagram understanding benchmark focused on scientific and educational visual question answering.

Which model scores highest on AI2D test split?

Qwen3.6-35B-A3B by Alibaba Cloud currently leads with 92.7%.

How many models are evaluated on AI2D test split?

2 canonical model products have a qualifying score, backed by 6 distinct dated source rows.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Navigation

AI2D test split

Leaderboard · 2 models

Qwen3.6-35B-A3B

Nemotron 3 Nano Omni 30B A3B

AI2D test split leaderboard

Crop AI2D test split leaderboard

Benchmark score table (2 models)

Crop AI2D test split benchmark table

Crop AI2D test split published source rows

Compare top models

Definition and scoring

Quick answers

What does AI2D test split measure?

Which model scores highest on AI2D test split?

How many models are evaluated on AI2D test split?

Does this affect overall Lumina rank?

AI2D test split

Leaderboard · 2 models

Qwen3.6-35B-A3B

Nemotron 3 Nano Omni 30B A3B

AI2D test split leaderboard

Crop AI2D test split leaderboard

Benchmark score table (2 models)

Crop AI2D test split benchmark table

Crop AI2D test split published source rows

Compare top models

Definition and scoring

Quick answers

What does AI2D test split measure?

Which model scores highest on AI2D test split?

How many models are evaluated on AI2D test split?

Does this affect overall Lumina rank?

Leaderboard · 2 models

Qwen3.6-35B-A3B

Nemotron 3 Nano Omni 30B A3B

Benchmark score table (2 models)

Compare top models

Definition and scoring

Quick answers

What does AI2D test split measure?

Which model scores highest on AI2D test split?

How many models are evaluated on AI2D test split?

Does this affect overall Lumina rank?

More Multimodal benchmarks

Leaderboard · 2 models

Qwen3.6-35B-A3B

Nemotron 3 Nano Omni 30B A3B

Benchmark score table (2 models)

Compare top models

Definition and scoring

Quick answers

What does AI2D test split measure?

Which model scores highest on AI2D test split?

How many models are evaluated on AI2D test split?

Does this affect overall Lumina rank?

More Multimodal benchmarks